Author name: Han Liu, Jiaqi Li, Zhi Xu, Xiaotong Zhang, Xiaoming Xu, Fenglong Ma, Yuanman Li, Hong Yu

arXiv:2604.16499v1 Announce Type: new
Abstract: Black-box adversarial attack on vision-language pre-trained models is a practical and challenging task, as text and image perturbations need to be considered simultaneously, and only the predicted result…